Data & Predictions
The first column of plots shows the number of favorites and retweets for xGPhilosophy’s end-of-match xG summary tweets (e.g. Man City (3.2) 1-0 Aston Villa (0.7)) since the account started to make regular tweets around the beginning of 2020.
Models have been created to predict each of these counts. (See second column.)
Taking the difference between the actual counts and the models’ predictions gives us an “over expected” number quantifying how unexpected a given tweet’s amount of engagement is. For example, a tweet that is predicted to receive 100 favorites and 10 retweets, but actually receives 200 favorites and 30 retweets tells us that the tweet received more attention (much more attention) than one might expect. This may tell us that the game was particularly interesting, perhaps due to something like a controversial, late-game VAR decision.
Prediction Explanation
SHAP